End of training
Browse files- README.md +13 -16
- adapter_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,7 +34,7 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate:
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
@@ -43,26 +43,23 @@ The following hyperparameters were used during training:
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 2
|
46 |
-
- training_steps:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.003 | 3.96 | 440 | 0.0348 |
|
64 |
-
| 0.0016 | 4.32 | 480 | 0.0408 |
|
65 |
-
| 0.0009 | 4.68 | 520 | 0.0395 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0261
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 3e-05
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 2
|
46 |
+
- training_steps: 400
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 1.1448 | 0.36 | 40 | 0.1779 |
|
54 |
+
| 0.0645 | 0.72 | 80 | 0.0358 |
|
55 |
+
| 0.0289 | 1.08 | 120 | 0.0301 |
|
56 |
+
| 0.0243 | 1.44 | 160 | 0.0282 |
|
57 |
+
| 0.0229 | 1.8 | 200 | 0.0263 |
|
58 |
+
| 0.0197 | 2.16 | 240 | 0.0260 |
|
59 |
+
| 0.0165 | 2.52 | 280 | 0.0258 |
|
60 |
+
| 0.0163 | 2.88 | 320 | 0.0255 |
|
61 |
+
| 0.014 | 3.24 | 360 | 0.0262 |
|
62 |
+
| 0.0123 | 3.6 | 400 | 0.0261 |
|
|
|
|
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218196746
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5cd2658e0e7ba6f153322fd68774ae0a038151a513b533c8c5c5262e2ea146d
|
3 |
size 218196746
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f387d87d263c4265b24a4fda94152600a997b452545a50195ad69fe6a0688fbe
|
3 |
size 4984
|